Edge-based IVD segmentation system

Author

Aboul-Yazeed, Rasha S. ; Mohamed, Abdalla S. A. ; El-Bialy, Ahmed

Author_Institution

Syst. & Biomed. Eng. Dept., Cairo Univ., Cairo, Egypt

fYear

2014

fDate

17-20 Feb. 2014

Firstpage

87

Lastpage

90

Abstract

Computer-aided diagnosing (CAD) and computer-assisted surgery (CAS) systems for spine and intervertebral disc (IVD) necessitate highly speed, minimal memory usage and accurate segmentation system because such system has a direct impact on spinal disease diagnosis and surgical planning. An unsupervised edge-based IVD segmentation system is proposed and validated on eight different lower back pain patients with MR sagittal and axial plane images. It achieves 0.98275, 0.9924 mean dice similarity coefficient (DSC) and 0.9733, 0.9735 mean area under the receiver operating characteristic (ROC) curve for sagittal and axial planes respectively. It requires averages of 26.017s and 431MB of memory usage for axial plane.

Keywords

biomedical MRI; bone; diseases; edge detection; image segmentation; medical image processing; surgery; CAD; CAS; DSC; IVD; MR axial plane images; MR sagittal plane images; ROC; computer-aided diagnosing systems; computer-assisted surgery systems; dice similarity coefficient; intervertebral disc; receiver operating characteristic curve; spinal disease diagnosis; spine; surgical planning; unsupervised edge-based IVD segmentation system; Accuracy; Biomedical imaging; Design automation; Image edge detection; Image segmentation; Memory management; Morphological operations;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering (MECBME), 2014 Middle East Conference on

Conference_Location

Doha

Type

conf

DOI

10.1109/MECBME.2014.6783213

Filename

6783213